@inproceedings{hua-etal-2020-attention,
title = "Attention-Based Graph Neural Network with Global Context Awareness for Document Understanding",
author = "Hua, Yuan and
Huang, Zheng and
Guo, Jie and
Qiu, Weidong",
editor = "Sun, Maosong and
Li, Sujian and
Zhang, Yue and
Liu, Yang",
booktitle = "Proceedings of the 19th Chinese National Conference on Computational Linguistics",
month = oct,
year = "2020",
address = "Haikou, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2020.ccl-1.79",
pages = "853--862",
abstract = "Information extraction from documents such as receipts or invoices is a fundamental and crucial step for office automation. Many approaches focus on extracting entities and relationships from plain texts, however, when it comes to document images, such demand becomes quite challenging since visual and layout information are also of great significance to help tackle this problem. In this work, we propose the attention-based graph neural network to combine textual and visual information from document images. Moreover, the global node is introduced in our graph construction algorithm which is used as a virtual hub to collect the information from all the nodes and edges to help improve the performance. Extensive experiments on real-world datasets show that our method outperforms baseline methods by significant margins.",
language = "English",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hua-etal-2020-attention">
<titleInfo>
<title>Attention-Based Graph Neural Network with Global Context Awareness for Document Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Hua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weidong</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Haikou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Information extraction from documents such as receipts or invoices is a fundamental and crucial step for office automation. Many approaches focus on extracting entities and relationships from plain texts, however, when it comes to document images, such demand becomes quite challenging since visual and layout information are also of great significance to help tackle this problem. In this work, we propose the attention-based graph neural network to combine textual and visual information from document images. Moreover, the global node is introduced in our graph construction algorithm which is used as a virtual hub to collect the information from all the nodes and edges to help improve the performance. Extensive experiments on real-world datasets show that our method outperforms baseline methods by significant margins.</abstract>
<identifier type="citekey">hua-etal-2020-attention</identifier>
<location>
<url>https://aclanthology.org/2020.ccl-1.79</url>
</location>
<part>
<date>2020-10</date>
<extent unit="page">
<start>853</start>
<end>862</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Attention-Based Graph Neural Network with Global Context Awareness for Document Understanding
%A Hua, Yuan
%A Huang, Zheng
%A Guo, Jie
%A Qiu, Weidong
%Y Sun, Maosong
%Y Li, Sujian
%Y Zhang, Yue
%Y Liu, Yang
%S Proceedings of the 19th Chinese National Conference on Computational Linguistics
%D 2020
%8 October
%I Chinese Information Processing Society of China
%C Haikou, China
%G English
%F hua-etal-2020-attention
%X Information extraction from documents such as receipts or invoices is a fundamental and crucial step for office automation. Many approaches focus on extracting entities and relationships from plain texts, however, when it comes to document images, such demand becomes quite challenging since visual and layout information are also of great significance to help tackle this problem. In this work, we propose the attention-based graph neural network to combine textual and visual information from document images. Moreover, the global node is introduced in our graph construction algorithm which is used as a virtual hub to collect the information from all the nodes and edges to help improve the performance. Extensive experiments on real-world datasets show that our method outperforms baseline methods by significant margins.
%U https://aclanthology.org/2020.ccl-1.79
%P 853-862
Markdown (Informal)
[Attention-Based Graph Neural Network with Global Context Awareness for Document Understanding](https://aclanthology.org/2020.ccl-1.79) (Hua et al., CCL 2020)
ACL